Abstract— In their interactions with the world robots inevitably face equivalent action choices, situations in which multiple actions are equivalently applicable. In this paper, ...
This work addresses the problem of efficiently learning action schemas using a bounded number of samples (interactions with the environment). We consider schemas in two languages-...
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
The association of perception and action is key to learning by observation in general, and to programlevel task imitation in particular. The question is how to structure this info...